Justin Norris

I’m seeing some strange behavior this afternoon, not sure if its connected

How can I fix / recover from these errors? Thanks!

Remi Do you know if a Dust agent has access to its own metadata, such as the conversation ID? The use case is I have a Dust app built to post the results of a task to Zapier, so it can be used in downstream orchestration I want the Zapier automation to be able to reference the same conversation in Dust, either to post follow-ups to it or to use it as a unique identifier So my idea was to include the Dust conversation ID in the dataset referenced by the app, so its included in the webhook submission to Zapier, but I wasn’t sure if the agent had access to its own properties in this way and could send it reliably

I have a research agent using Claude 4 that works well much of the time, but in certain scenarios hits a context window error repeatedly (this is dependent on the company being researched, likely due to scarcity of information prompting the agent to do more and more searches) The challenge is that once the error hits, the previous chain of reasoning and tool use disappear, which makes it very difficult to analyze where in the process the agent is failing, which in turn makes it difficult to optimize the instructions Is there a way to preserve the information up to the point the error hit so that we can debug more easily?

Just want to say, I am really appreciating the ability for one agent to use another as a tool. I use it constantly now and it unlocks so many possibilities. Amazing feature 👍